© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1743
    Prev
    Next
    INDEX
    Explanations

    maximum, optimal values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.76
    oa̍t
    -0.73
    TagMode
    -0.73
    ftagPool
    -0.70
     lenker
    -0.69
    SourceChecksum
    -0.65
     otomatig
    -0.65
     dévelo
    -0.64
     Vikipedi
    -0.64
    HtmlAttribute
    -0.62
    POSITIVE LOGITS
    同時
    0.49
    itinéraire
    0.47
     Meanwhile
    0.46
    同时
    0.45
    mappedBy
    0.45
    ̀n
    0.45
     correctly
    0.43
     simultaneously
    0.42
     simultaneous
    0.42
    putstr
    0.42
    Activations Density 0.007%

    No Known Activations